Hiring: Research Engineer, AI Safety & Alignment Company: Character.ai Location: Redwood City, CA Job Posted Time: 2026-09-16 15:59:13 Employment Type: Full-time Target Skills & Keywords: AI Safety, AI Alignment, Large Language Models (LLMs), RLHF, Interpretability, Adversarial Testing, Transformers, Reinforcement Learning, Model Evaluation, Bias Mitigation, Fine-tuning, GPUs, Data Pipelines, Distributed Training, Kubernetes, Docker, Cloud, Explainable AI (XAI), A/B Testing, Python, Production Code Experience: - PhD (or equivalent experience) in Computer Science, Machine Learning, or a related discipline - Experience working with GPUs (training, serving, debugging) - Experience with data pipelines and data infrastructure - Nice to have: experience with product experimentation and A/B testing - Nice to have: experience training large models in a distributed setting - Nice to have: familiarity with ML deployment and orchestration (Kubernetes, Docker, cloud) - Nice to have: experience with explainable AI (XAI) and interpretability techniques - Nice to have: research in AI safety, alignment, ethics, or a related area - Nice to have: publications in relevant academic journals or conferences in machine learning Required Skills: - Ability to write clear and clean production-facing and training code - Strong understanding of modern machine learning techniques, particularly transformers and reinforcement learning, with a focus on their safety implications - Developing and implementing novel evaluation methodologies and metrics to assess safety and alignment of large language models - Research and development of cutting-edge techniques for model alignment, value learning, and interpretability - Conducting adversarial testing to uncover vulnerabilities and failure modes - Analyzing and mitigating biases, toxicity, and harmful behaviors in LLMs through techniques like RLHF and fine-tuning - Collaborating with engineering and product teams to translate safety research into scalable solutions - Staying current with the latest advancements in AI safety research and contributing to the academic community Qualifications: - Passion for the responsible development of AI and dedication to solving complex safety challenges - Knowledge of the broader societal and ethical implications of AI, including policy and governance (nice to have) - Strong research mindset bridging theoretical research and practical application - Ability to contribute to the broader scientific community through publications and presentations Compensation: Not specified in the job posting. Interested candidates, please apply directly through the job posting on company's career page or try via AI auto apply on this platform. Don’t miss this opportunity to join a forward-thinking team!